Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.9288. Min Act: -0.0000

Data Index: 248747 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.6984. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.5560. Min Act: -0.0000

Data Index: 241471 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.2714. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.0238. Min Act: -0.0000

Data Index: 30943 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.0030. Min Act: -0.0000

Data Index: 620272 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.1075. Min Act: -0.0000

Data Index: 720974 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.0676. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.0373. Min Act: -0.0000

Data Index: 866898 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 4.9288. Min Range: -4.9288

Max Act: 4.0685. Min Act: -0.0000

Data Index: 645653 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.7578. Min Act: -0.0000

Data Index: 1325572 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.7230. Min Act: -0.0000

Data Index: 806084 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.6777. Min Act: -0.0000

Data Index: 56437 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.6126. Min Act: -0.0000

Data Index: 73755 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.7671. Min Act: -0.0000

Data Index: 895053 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.5545. Min Act: -0.0000

Data Index: 935841 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.5329. Min Act: -0.0000

Data Index: 247165 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.5191. Min Act: -0.0000

Data Index: 237128 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.3353. Min Act: -0.0000

Data Index: 450614 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 4.9288. Min Range: -4.9288

Max Act: 3.4714. Min Act: -0.0000

Data Index: 942850 (C4 (Web Text))

Max Activating Token Index: 830